PROTEA: Securing Robot Task Planning and Execution
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918283321540608 |
|---|---|
| author | Altaweel, Zainab Nahian, Mohaiminul Al Juettner, Jake Rakin, Adnan Siraj Zhang, Shiqi |
| author_facet | Altaweel, Zainab Nahian, Mohaiminul Al Juettner, Jake Rakin, Adnan Siraj Zhang, Shiqi |
| contents | Robots need task planning methods to generate action sequences for complex tasks. Recent work on adversarial attacks has revealed significant vulnerabilities in existing robot task planners, especially those built on foundation models. In this paper, we aim to address these security challenges by introducing PROTEA, an LLM-as-a-Judge defense mechanism, to evaluate the security of task plans. PROTEA is developed to address the dimensionality and history challenges in plan safety assessment. We used different LLMs to implement multiple versions of PROTEA for comparison purposes. For systemic evaluations, we created a dataset containing both benign and malicious task plans, where the harmful behaviors were injected at varying levels of stealthiness. Our results provide actionable insights for robotic system practitioners seeking to enhance robustness and security of their task planning systems. Details, dataset and demos are provided: https://protea-secure.github.io/PROTEA/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07186 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PROTEA: Securing Robot Task Planning and Execution Altaweel, Zainab Nahian, Mohaiminul Al Juettner, Jake Rakin, Adnan Siraj Zhang, Shiqi Robotics Robots need task planning methods to generate action sequences for complex tasks. Recent work on adversarial attacks has revealed significant vulnerabilities in existing robot task planners, especially those built on foundation models. In this paper, we aim to address these security challenges by introducing PROTEA, an LLM-as-a-Judge defense mechanism, to evaluate the security of task plans. PROTEA is developed to address the dimensionality and history challenges in plan safety assessment. We used different LLMs to implement multiple versions of PROTEA for comparison purposes. For systemic evaluations, we created a dataset containing both benign and malicious task plans, where the harmful behaviors were injected at varying levels of stealthiness. Our results provide actionable insights for robotic system practitioners seeking to enhance robustness and security of their task planning systems. Details, dataset and demos are provided: https://protea-secure.github.io/PROTEA/ |
| title | PROTEA: Securing Robot Task Planning and Execution |
| topic | Robotics |
| url | https://arxiv.org/abs/2601.07186 |